Publications

Detailed Information

QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars

DC Field Value Language
dc.contributor.authorWinkler, Alexander-
dc.contributor.authorWon, Jungdam-
dc.contributor.authorYe, Yuting-
dc.date.accessioned2024-05-08T05:35:25Z-
dc.date.available2024-05-08T05:35:25Z-
dc.date.created2024-05-08-
dc.date.issued2022-
dc.identifier.citationPROCEEDINGS SIGGRAPH ASIA 2022, p. 2-
dc.identifier.urihttps://hdl.handle.net/10371/201174-
dc.description.abstractReal-time tracking of human body motion is crucial for interactive and immersive experiences in AR/VR. However, very limited sensor data about the body is available from standalone wearable devices such as HMDs (Head Mounted Devices) or AR glasses. In this work, we present a reinforcement learning framework that takes in sparse signals from an HMD and two controllers, and simulates plausible and physically valid full body motions. Using high quality full body motion as dense supervision during training, a simple policy network can learn to output appropriate torques for the character to balance, walk, and jog, while closely following the input signals. Our results demonstrate surprisingly similar leg motions to ground truth without any observations of the lower body, even when the input is only the 6D transformations of the HMD. We also show that a single policy can be robust to diverse locomotion styles, different body sizes, and novel environments.-
dc.language영어-
dc.publisherASSOC COMPUTING MACHINERY-
dc.titleQuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars-
dc.typeArticle-
dc.identifier.doi10.1145/3550469.3555411-
dc.citation.journaltitlePROCEEDINGS SIGGRAPH ASIA 2022-
dc.identifier.wosid001074614400036-
dc.identifier.scopusid2-s2.0-85143970989-
dc.citation.startpage2-
dc.description.isOpenAccessY-
dc.contributor.affiliatedAuthorWon, Jungdam-
dc.type.docTypeProceedings Paper-
dc.description.journalClass1-
dc.subject.keywordAuthorMotion Tracking-
dc.subject.keywordAuthorCharacter Animation-
dc.subject.keywordAuthorReinforcement Learning-
dc.subject.keywordAuthorWearable Devices-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Related Researcher

  • College of Engineering
  • Dept. of Computer Science and Engineering
Research Area Computational Performance, Computer Graphics, Machine Learning, Robotics

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share